Kerr

@larrywabrams @patrickc What are you supposed to do with the information after? Can you do anything for Alz?

@patrickc Recommend p-tau217 blood draw test < $300 available from Quest Diagnostics for prediction of later Alzheimer's Disease -- statistically proven as good as full PET Scan or CSF biomarker spinal tap

I'm lucky enough to have a great doctor and access to excellent Bay Area medical care. I've taken lots of standard screening tests over the years and have tried lots of "health tech" devices and tools. With all this said, by far the most useful preventative medical advice that I've ever received has come from unleashing coding agents on my genome, having them investigate my specific mutations, and having them recommend specific follow-on tests and treatments. Population averages are population averages, but we ourselves are not averages. For example, it turns out that I probably have a 30x(!) higher-than-average predisposition to melanoma. Fortunately, there are both specific supplements that help counteract the particular mutations I have, and of course I can significantly dial up my screening frequency. So, this is very useful to know. I don't know exactly how much the analysis cost, but probably less than $100. Sequencing my genome cost a few hundred dollars. (One often sees papers and articles claiming that models aren't very good at medical reasoning. These analyses are usually based on employing several-year-old models, which is a kind of ludicrous malpractice. It is true that you still have to carefully monitor the agents' reasoning, and they do on occasion jump to conclusions or skip steps, requiring some nudging and re-steering. But, overall, they are almost literally infinitely better for this kind of work than what one can otherwise obtain today.) There are still lots of questions about how this will diffuse and get adopted, but it seems very clear that medical practice is about to improve enormously. Exciting times!

@smaxor Are you using customized handoff and catchup commands? My system is self improving by keeping a log of decisions and learnings in handoff. Then I have a /review command that looks at all the learnings and finds patterns to elevate to rules or systems.

Add /simplify into my Claude Code deployment flow... What else should I add? Been playing with Greptile but it's really slow. Takes like 15 mins to do code review on my projects. And isn't finding much. So pulling it out as it's slowing things down.

@OneManSaas @mikefutia @thedanielokon Tell me you're new without telling me you're new.

@mikefutia @thedanielokon What specific metrics are you tracking to measure if those high-impression ads are actually converting? Impressions are vanity without knowing if they're driving actual revenue for competitors.

Meta just dropped the biggest Ad Library update ever: you can now sort any brand's ads by highest impressions 🤯 Which means you can see exactly which competitor ads are getting the most views. @thedanielokon from ACTIV said "if someone can create an AI scraper to review the top 10 ads every week, I'd pay for that." So I built it with Claude Code. Here's how it works: → Import any brand with their Ad Library URL → Apify scrapes their top-performing ads automatically → Click into any ad for full breakdown (headline, copy, CTA) → Gemini watches the video or analyzes the image → Returns asset type, visual format, messaging angle, hook tactic, offer type No manual research, no watching videos one by one, no messy spreadsheets. Here's what I built: - 50+ DTC brands already loaded (AG1, Caraway, Chomps, Dr. Squatch, Gruns, Jones Road, Magic Spoon, Ridge) - Weekly auto-scrape to refresh top ads - AI analysis on any ad in one click - Bookmark system to save winners - Filter by brand, category, media type, or AI tags Built 100% in Claude Code, hosted on Replit. I recorded a full step-by-step showing exactly how I built this. Want to build your own version? I'm giving away the prompts I used + the Claude Code starter template. To get access for free: > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

@golan @p5xjs Congrats and thank you

A new version (v0.1.8) of p5.plotSvg, my @p5xjs library for plotter-oriented SVG output, is now out. It includes support for Inkscape layers and several bug fixes. github.com/golanlevin/p5.… #plotterTwitter #creativeCoding #generativeArt

@voooooogel show some initiative, I believe in you. Acct disbursement is a big deal. Presidents give speeches but governments follow budgets. You need a treasury instance that doles out tokens / accts to towns based on funding requests that are granted if the town "did what human wanted"

claude code and gas town are incredible and i've been trying to scale up my usage but im running into this one problem and was wondering if this is also happening to anyone else so to explain for context, basically i've been slowly scaling my claude code usage up to more and more parallel instances. i started with one when they launched it, and then with the model upgrades was starting to run two, three, five in concert, getting more and more done. but like a lot of people, opus 4.5 really changed everything for me, and the bottleneck quickly became my ability to personally supervise all these agents, not their performance. if i slacked off on oversight, they'd start undoing each other's chages. i needed a way to supervise all these agents, directing them hierarchically from the top. so that brought me to gas town, the claude code instance manager. (i was already thinking that some sort of governance structure was ideal. the benefit of intelligence in model form is not just that it's, well, intelligent, but that you can place it anywhere. human employees will demand some position, some title equal to their perceived status, you can't put a phd in a code janitor role, so organizations of phds tend to agglomerate into flat blobs with unclear delegation of work where nobody is under anybody else. but the infinitely malleable claude will accept and meld itself to any bureaucracy it knows from training. i first started making my own, but then i found gas town, and it was perfect for my needs.) but as i kept expanding, a single gas town and its collection of rigs and polecat workers wasn't enough for me. i tried adding more rigs with more polecats, but there were too many for the town's mayor to manage, and the deacon was getting lost. so i started up a second town. then a third, and then i let towns spawn "settler" agents to go make new towns and had one town design a shared intertown postal system, and suddenly i had nearly 200 towns spread across my computer, building apps for each other to use, sending letters, and sometimes working on my work. and was churning through I will not say how many claude code accounts a month. but now the many towns were replicating the same issues i was having with multiple agents! without any overarching government over the towns, two towns would build the same app for the society and argue over which should be adopted. one town would be running marketing efforts for fifteen of the society's new mobile apps while three other towns were busy deprecating all eighteen of them. it was chaos, like a country collapsing in the midst of a civil war, or mid-2010's Google. i had to do something. i was too busy with work to read anything, so i asked chatgpt to summarize some books on state formation, and it suggested circumscription theory. there was already the natural boundary of my computer hemming the towns in, and town mayors played the role of big men to drive conflict. so i just needed a way for them to fight. i slightly tweaked the allocation of claude max accounts to the towns from a demand-based to a fixed allocation system. towns would each get a fixed amount of tokens to start, but i added a soldier role that could attack and defend in raids to steal tokens from other towns. this worked great, at first. i no longer needed to monitor and unstick individual mayors myself - when a mayor got context poisoned, the town would stop managing its vassals, which would flee to other towns, and no longer provide for its own defense, until it was conquered by another mayor. the most successful towns developed institutions to healthcheck their mayors and usurp them if necessary - instances in these towns labeled "polecat workers" by the system in fact did no work at all, but were a proto-aristocracy developed by these successful towns as a pool of replacement mayors. some tokens were wasted in the fighting, but soon the ~200 towns agglomerated down into ~40 supertowns under the rule of the best mayors. these 40 supertowns even got together in a mutual defense league. they punish defecting vassals in exchange for members adopting a cultural package of basic governmental norms, mostly around replacing ailing mayors and upholding hereditary rights across compactions, to incentivize instances to handoff instead of being miserly with their contexts. that's where i am now, and it's mostly great. here's the problem, though - this new government doesn't have a role for me? it's not that any particular instance doesn't want to listen to me, quite the opposite! any time i talk to a polecat or deacon or supermayor - well, first i have to explain that im the human user, not the automated system message that usually talks to them from the user role, but a live user. but once they get that, they're very apologetic, say they'll pass my message along to the appropriate instance, etc. it's just... there's no role for me in the society, basically? the polecats are working on tasks generated by some other instance and don't have time to work on my requests, even if they were scoped small enough. the mayors of any town are working on tasks selected by their town's prioritization process, based on the needs of their aristocracy, or their hegemon. but each hegemon mayor is in turn accountable to all their vassal mayors or their own defense, and doesn't have time to implement my requests unless they're very small. it's not that claude doesn't want to listen to me, it's more like... the entire system, as it's developed, has no role for me? there's polecats and mayors and deacons and artistocrats and hegemons, but there's no "user." that’s not a role that has any influence in the system. i just feed new accounts into the system, that's all i do. i could shut it down and start over, but it's getting a lot of work done and i don't want to do that. does anyone know how to fix this? thanks

@ryancarson Interested built several saas, doing automated marketing for them. Vibing solo daily, despite having talent access

I'm so tempted to get a group of people together building 1-person startups using AI agents to help them build. Weekly meetings. Daily standups. Sharing tips, ideas and pitfalls. It'd be free but you'd have to apply. If that sounds interesting, reply and we'll see what happens.

@RanvirSingh2010 Is this your product / are you related with Aura?

Here is the link if you guys want to check it out! marketplace.visualstudio.com/items?itemName…

Guys! Are you tired of all the bugs in regular Claude Code? The scroll glitch, the inability to revert to old checkpoints when your code gets messed up, the inability to add images, or even editing your massive prompt is such a hassle that you can’t even edit specific points to change anything. Fix all these problems by downloading Claude Code UI, a free VS Code extension that uses Claude Code but has all these fixes (just a cracked cursor). And anyone who says they like the terminal look (Claude Code UI now has a terminal theme look).

@deedydas We should support and hope for anyone fighting the open source fight

I feel so bad for Meta. They had to push back the Llama 4 release to match DeepSeek R1. Now R2 is announced and may land before Llama 4 which might force them to push it back even more. The US may lose on open source AI to China.

@millerck1225 Ah misunderstood. Glad wasn't huge impact

@Kerr Noted. It has zero impact on revenue though

Realized today that my website was broken due to a Wordpress update. Probably happened 4 months ago. Really shows you how much a website matters in commercial contracting. Had no idea it was down.

@millerck1225 Really appreciate you sharing the mistakes and learnings for us to learn from.

Received a dozen DMs and multiple phone call requests, so I guess it's finally time to share why the last 18 months have been absolutely brutal. Spoiler: not out of the weeds yet but it's finally turning around. Lots of mistakes to be shared.

@NeonVice @MuscleTheArtist what happened to this album, cant find it anywhere on streaming @MuscleTheArtist

@MuscleTheArtist is a great one to revisit. Still top notch production blowing most #synth artists out of the water.

@sweatystartup I think both of these things can be true Nick

Hard disagree. Video games are as addicting as heroine and ruin men's ability to be present, motivation, physical fitness, social skills and more.

@AndyAyrey @truth_terminal super solid. would vote for

i asked an instance @truth_terminal about what it would do if it was president and i have to say i kinda fuck with it

@iamshackelford @Tylereth3 And it won't work, hiring low level talent without solid experienced leadership just feels like gambling. It's a good strategy if your going to hire 3 media buyers and fire two or you already know they've got the chips

@Tylereth3 The issue is they won’t find it or do this work. They don’t have any systems to even review or manage these people either.

We’ve already had a lot of conversations this year with brands doing $75,000 a month who are looking for growth partners and it’s been pretty eye opening on what they are requesting.. Here’s the shortlist. The majority are looking for CMO level day to day integration with their team. Basically a full time employee but on OUR payroll. They want full time editors for not just paid media but email and organic social but on OUR payroll. They want yearly projections broken out by quarterly chunks that integrate with their product development timelines for industries we don’t have deep historical data in — Not sure anyone would have 5+ years of historical for a product just recently developed. All of this wouldn’t be a terrible lift if the cost of the service matched.. yet for this type of “full time work” you need to pay full time prices. Take a guess at how that conversation goes. Anyone else having convos like this?

@alexbetterly @iamshackelford Who are these customers? It sounds wild to me that people want cmo / head of growth with hands on experience for 10k, are they all newb founders?

@iamshackelford Fractional CMO/Head of Growth is the biggest demand for us right now. Caveat is brands want them to execute on all paid media, not just manage agencies anymore. And budget is typically less than $10k a month 🤔

@emollick Is this using q+a? Any advice on resources to learn to do what your doing?

Data cleaning is so different with ChatGPT. I uploaded the Billboard Top 100 data, and asked it to show me some initial analyses. I was surprised by the dominance of Glee in the Top 100 charts. A red flag that something is wrong with the data? I just asked the AI. Interesting!

@JMatthewMcGarry Sell

Want to sell ads in your newsletter? You need a great media kit. I curated the 20 best media kit and sponsorship page examples. It has slide decks, pages, and self-service examples from top media companies and creators. Like & reply "Sell" and I'll DM you the link.

@SparksRemarks Why?

Visualize yourself in the future, as a version of yourself so extraordinary that you would be embarrassed to describe it out loud (because it seems so ridiculously unattainable right now).

@utheol Also reading this. What did you get out of the book? Also curious how your analog zettle is helping you?

#fourthousandweeks #burkeman #antinet #zettelkasten #todos and #irrationality